© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 4910
    Prev
    Next
    INDEX
    Explanations

    time passing quickly

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çīĪæĿĥå½Ĵ
    -0.09
     Ñĥдален
    -0.09
    amped
    -0.09
    çŁŃæŶéĹ´åĨħ
    -0.08
    亿åIJ¨
    -0.08
    å¿«æīĭ
    -0.08
    æī¶
    -0.08
    åĪ¶
    -0.08
    çłģ
    -0.08
    åIJİèĢħ
    -0.08
    POSITIVE LOGITS
    ä»įæĺ¯
    0.09
    çļĦä¸ĢéĿ¢
    0.08
    pector
    0.08
    çĦ¶æĺ¯
    0.08
    éĿĸ
    0.08
     Gir
    0.08
    èŀ¯
    0.08
    umu
    0.07
     Heidi
    0.07
    à¹Ħ
    0.07
    Activations Density 0.010%

    No Known Activations